* ✨ feat: add GPT-5.4 model support and fix reasoning payload pruning
- Add GPT-5.4 model card to model-bank
- Update planCardModels to use gpt-5.4
- Add gpt-5.4 to responsesAPIModels
- Fix pruneReasoningPayload to strip logprobs/top_logprobs for reasoning models
- Add logprobs, top_logprobs to ChatStreamPayload type
- Extend reasoning_effort to include none and xhigh
- Add success log for non-fallback requests in RouterRuntime
- Fix log parameter mismatch in RouterRuntime
Fixes LOBE-5735
* 🐛 fix: match gpt-5.4 to gpt5_2ReasoningEffort in openrouter and vercelaigateway
* 🐛 fix: update OpenRouterReasoning effort type to include none and xhigh
* 🐛 fix: use tiered pricing for gpt-5.4 based on 272K token threshold
* 🌐 chore: update i18n translations
* 🐛 fix: update claude-sonnet model version to 4-6 in planCardModels
* ✨ feat: add GPT-5.4 Pro model support
* 🐛 fix: remove dated snapshot for gpt-5.4-pro in responsesAPIModels
* 🐛 fix: add tierBy support for cross-unit tiered pricing threshold
OpenAI charges output at 1.5x when INPUT exceeds 272K tokens.
The tiered strategy previously only checked the unit's own quantity
to select a tier. Added optional tierBy field to TieredPricingUnit
so output/cacheRead tiers can reference input quantity for selection.
* 🐛 fix: use totalInputTokens for tiered pricing tier selection
Tiered pricing tiers should be determined by total prompt size
(totalInputTokens), not each unit's own quantity. This fixes output
and cacheRead being charged at the wrong tier rate when the prompt
exceeds the threshold but the individual unit quantity does not.
* ♻️ refactor: replace minImageSize with width/height min/max constraints
Refactor image dimension validation from a single `minImageSize` value
to flexible `width`/`height` objects with `min`/`max`, consistent with
the `duration` field's min/max pattern.
* ♻️ refactor: handle single-axis constraints in dimension error messages
Build dimension constraint text dynamically (e.g. "width ≥ 300px" or
"width ≥ 300px, height ≥ 300px") instead of interpolating raw
minWidth/minHeight values, preventing "300xundefinedpx" when only one
axis is constrained.
* ♻️ refactor(video): add max dimension constraint per official docs
Seedance image dimensions: 300-6000px per official documentation.
* ✨ feat(video): add aspect ratio validation for image uploads
Support aspectRatio constraint (width/height) with min/max in schema.
Seedance config: aspectRatio { min: 0.4, max: 2.5 } per official docs.
* ♻️ refactor(locales): add image dimension validation messages for multiple languages
* 🔧 chore(release): bump version to v2.1.27 [skip ci]
* chore: update sync main to canary workflow
* 🐛 fix: update @lobehub/ui version and refactor dynamic import handling (#12260)
* ✨ feat: add hotfix workflow and script for automated hotfix management
Signed-off-by: Innei <tukon479@gmail.com>
* 🔧 fix: refactor PR creation command to use execFileSync for improved reliability
Signed-off-by: Innei <tukon479@gmail.com>
* 🔧 chore: update @lobehub/ui version and refactor dynamic import handling
- Bump @lobehub/ui dependency from ^4.35.0 to ^4.36.2 in package.json.
- Refactor settingsContentToStatic.mts to simplify dynamic import processing by removing business feature checks.
- Add initialize.ts to enable immer's map set functionality.
- Correct import path in layout.tsx from 'initiallize' to 'initialize'.
Signed-off-by: Innei <tukon479@gmail.com>
* 🔧 chore: update @types/react version in package.json
- Bump @types/react dependency from ^19.2.9 to 19.2.14.
- Add @types/react version to overrides section for consistency.
Signed-off-by: Innei <tukon479@gmail.com>
* 🔧 chore: enhance auto-tag-release workflow for strict semver validation
- Updated regex to match strict semantic versioning format, allowing for optional prerelease and build metadata.
- Added validation step to ensure the version is a valid semver before proceeding with the release process.
Signed-off-by: Innei <tukon479@gmail.com>
* 🗑️ chore: remove defaultSecurityBlacklist test file
- Deleted the test file for DEFAULT_SECURITY_BLACKLIST as it is no longer needed.
- This cleanup helps maintain a more streamlined test suite.
Signed-off-by: Innei <tukon479@gmail.com>
* 🔧 chore: update localization files for multiple languages
- Improved translations in Arabic, Bulgarian, German, English, and Spanish for chat and tool-related strings.
- Enhanced descriptions for various parameters and added new keys for file handling and security warnings.
- Adjusted phrasing for clarity and consistency across languages.
Signed-off-by: Innei <tukon479@gmail.com>
* 🔧 chore: update PR comment script to include Actions Artifacts link
- Modified the PR comment generation script to accept an additional artifactsUrl parameter.
- Updated the comment format to include both Release download and Actions Artifacts links for better accessibility.
Signed-off-by: Innei <tukon479@gmail.com>
---------
Signed-off-by: Innei <tukon479@gmail.com>
* 🐛 chore(hotfix): bump version to v2.1.28 [skip ci]
* chore: update secrets token
---------
Signed-off-by: Innei <tukon479@gmail.com>
Co-authored-by: rdmclin2 <rdmclin2@gmail.com>
Co-authored-by: Arvin Xu <arvinx@foxmail.com>
Co-authored-by: Innei <i@innei.in>
* 🐛 fix: show notification when file upload fails due to storage plan limit
Previously, when file storage exceeded the plan limit, the TRPC
middleware threw a FORBIDDEN error that was silently swallowed by
the upload components with no user feedback. Now `uploadWithProgress`
catches this specific error and displays a notification guiding
users to upgrade or free up space.
* 🌐 chore: run i18n for upload storage limit error message
* 🌍 i18n: update model descriptions across multiple languages
Added new model descriptions and improved existing ones in Arabic, Bulgarian, German, French, Italian, Japanese, and Korean locales. This update enhances the clarity and detail of model capabilities, ensuring better user understanding and accessibility.
- Refactor webServer.ts with better process coordination and lock file mechanism
- Add mock S3 env vars to prevent initialization errors
- Complete missing i18n translations across all locales
* ✨ feat: support to show working dir
* fix style
* update docs
* update topic
* refactor to use chat config
* inject working Directory
* update i18n
* fix tests
